490 likes | 604 Views
Head and Neck Lymph Node Region Delineation with Auto-segmentation and Image Registration. Chia -Chi Teng Department of Electrical Engineering University of Washington. Outline. Introduction Related Work Lymph Node Region Contouring with Image Registration
E N D
Head and Neck Lymph Node Region Delineation with Auto-segmentation and Image Registration Chia-Chi Teng Department of Electrical Engineering University of Washington
Outline • Introduction • Related Work • Lymph Node Region Contouring with Image Registration • Automatic Segmentation of Landmark Structures • Geometrical Feature Based Similarity • Results • Conclusion
Context • 3D Conformal Radiotherapy (beams are shaped to match the tumor) • Intensity Modulated Radiation Therapy (controls intensity in small volumes)
Target Volumes • GTV / CTV / PTV
Motivation • Improve the process of target volume delineation for radiation therapy planning. • Objective: • Auto-contour lymph node regions. • Initial focus on head and neck.
Problem • Where are the lymph nodes? • Where are the lymph node regions? none of the structures are lymph nodes
Solution • Create reference (canonical) models. • Map reference nodal regions to patients.
Image Registration • Align the transformed reference image fR ° g to the target image fT . • Find the optimal set of transformation parameters m that maximize an image similarity function S: moptimal = argmaxmS(m)
Mattes’ Method • Similarity Function S(m) = -mutual_information( fR ° g, fT ) • Transformation Funciton g(x|m) = R(x - xC) – T(x - xC) + D(x|d) x = [x, y, z]T in the reference image coordinates.
Deformable Transformation • Control points (15*15*11). • Each control point is associated with a 3-element deformation vector d, describing x-, y-, z-components of the deformation.
Project Target Lymph Regions • Image registration aligns reference and target CT sets. • Apply result transformation g to reference lymph node regions. • Incorporate anatomical landmark correspondences. • Use surface mesh of outer body contour, mandible, hyoid …
Surface Warping • Shelton’s method used to find correspondences between surfaces. • Energy based surface mesh warping. E(C) = Esim(C) + aEstr(C) + bEpri(C) C is the function which maps points from reference surface SR to target surface ST .
Landmark Correspondence • The deformation z at landmark points zk = vk-uk uk: points from reference surface mesh SR. vk: corresponding locations on transformed reference surface SR° C matching the target surface mesh ST.
SurfaceST SurfaceSR zk = vk-uk SR ° C
Using Landmark Correspondence • Deformation vectorsD(lj) are modified according to landmark correspondenceszkin the proximity of the control pointslj. • Landmark structures align better. • Faster convergence.
Compare Image Registration Results Reference Mattes w/ Landmark Target
Automatic Segmentation of Landmark Structures • Given: Cancer radiation treatment patient’s head and neck CT image. • Find: • Skull base & thoracic inlet. • Anatomical structures: • cervical spine (white) • respiratory tract (dark green) • mandible (turquoise) • hyoid (yellow) • thyroid cartilage • internal jugular veins (pink) • carotid arteries (dark yellow) • sternocleidomastoid muscles (light green, orange)
Method • 2D knowledge-based segmentation • Based on Kobashi’s work • Dynamic thresholding • Progressive landmarking • Combined with 3D active contouring • Do not require successful 2D segmentation on every axial slice • Initialize with 2D segmentation result
2D Segmentation Results A B C D E
2D/3D Iteration Identify objects that are easy to find, use them to find harder ones. 1 3 5 2 4 6
2D/3D Iteration – cont. 7 9 11 8 10 12
Geometrical Feature- Based Similarity • Given: A stored database DB of CT scans from prototypical reference head and neck cancer patients and a single query CT scan Q from a target patient. • Find: Similarity between Q and each database image d in DB in order to find the most similar database images {ds}.
Structures • Outer body contour • Mandible • Hyoid • Internal jugular veins
Feature Types • Simple numeric 3D regional properties: volume and extents. • Vector properties: relative location between structures. • Shape properties: surface meshes of structures.
Features for Similarity Measure • Volume and extents of the overall region • Normalized centroid of hyoid and mandible • 3D centroid difference vector between mandible and hyoid • 2D centroid difference vectors between hyoid and jugular veins • Surface meshes of mandible and outer body contour
= d ( TS , S ) max d ( Tp , S ) h R T T Î p S R Mesh Feature Distance • Register reference mesh SR and target mesh ST with Iterative Closest Point (ICP), result T. • Hausdorff distance between two aligned surface meshes, TSR and ST The Hausdorff distance is the maximum distance from any point in the transformed reference image to the test image.
Feature Vector Distance • Given feature vectors Fd and FQ for model d and query Qin the feature vector space RN. 1 é ù N 2 å = 2 D ( F , F ) w d ( F , F ) ê ú F d Q i i d Q i i ë û = i 1
Evaluation • Surface mesh distance after full image registration DH – slow. • Feature vector distance DF – fast. corr_coef(DH, DF) = 0.72 DH Images with small feature vector distance should produce the best results after registration. DF
Experiment Results • 50 head and neck patient CT sets. • 34 subjects are segmented. • 20 subjects with lymph node regions drawn by experts. • Image registration 20 * (20 – 1) = 380 total cases.
Auto-segmentation Results • Correct Segmentations
Auto-segmentation cont. • Incorrect Segmentations Carotid artery misidentified as Hyoid partly missing due to jugular vein due to surgery. too low inter-slice resolution.
Image Registration Results Success/Failure Time of Convergence
Quantitative Evaluation -Surface Mesh Distance DH(SR ° g, ST, n) : Hausdorff distance n: lymph node region Projected Region SR ° g Color is distance to truth. Ground Truth: Expert Drawn Target Region ST
Mattes distance larger than landmark distance. DH(SR ° g, ST, 1B) for all SR, ST. Measurement in centimeter.
Mean_distance(SR ° g, ST, 1B) for all SR, ST. Measurement in centimeter.
Similarity Evaluation • RH(i, Q) : the ith ranked reference subject for target Q based on the image registration results, DH. • RF(i, Q) :the ith ranked reference subject based on geometrical features, DF. P(RF(1, Q)=RH(1, Q)) = 80% P(RF(1, Q)=RH(2, Q)) = 10% P(RF(1, Q)=RH(3, Q)) = 4%
Similarity Evaluation Examples DH DH DF DF corr_coef(DH, DF) = 0.74 corr_coef(DH, DF) = 0.68
Similarity Evaluation – Surface Mesh Distance Measurement in centimeter. So its better to find the closest subject.
Qualitative Evaluation – 1.1 • Clinically acceptable target projection. Mattes Expert w/ Landmark Drawn
Qualitative Evaluation – 1.2 • Clinically acceptable target projection. Mattes Expert w/ Landmark Drawn
Qualitative Evaluation – 1.3 • Clinically acceptable target projection. Mattes Expert w/ Landmark Drawn
Qualitative Evaluation – 2 • Clinically unacceptable target projection. Mattes Expert w/ Landmark Drawn
Conclusion • Inter-subject image registration technique shows promise for lymph node region auto-contouring. • Knowledge-based auto-segmentation is useful for head and neck CT. • Fast similar subject search is possible and critical as reference database grows.
Future Work • Integrate and evaluated in a clinical environment. • Generalize to other types of cancer. • Regional lymphatic involvement prediction. • Improve image registration results. • Improve auto-segmentation results. • Validation logic • Knowledge-based 3D active contour constraints
Acknowledgement • Linda Shapiro • Ira Kalet • Jim Brinkley • David Haynor • David Mattes • Mark Whipple • Jerry Barker • Carolyn Rutter • Rizwan Nurani
Contributions • The first auto target contouring tool for radiation therapy. (AMIA 2002) • An auto-segmentation method combining 2D dynamic thresholding and 3D active contouring. (IEEE CBMS 2006) • An image registration method using landmark correspondences in conjunction with mutual information optimization. (IEEE ISBI 2006) • A patient similarity measurement using 3D geometrical features of anatomical structures. (IEEE ISBI 2007)